{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:RUSDF3FZYLFKVEOZTHLVS3B65B","short_pith_number":"pith:RUSDF3FZ","schema_version":"1.0","canonical_sha256":"8d2432ecb9c2caaa91d999d7596c3ee849f6eeef6231a70ae04ca47ed95d5ece","source":{"kind":"arxiv","id":"2502.04519","version":2},"attestation_state":"computed","paper":{"title":"GenVC: Self-Supervised Zero-Shot Voice Conversion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"eess.AS","authors_text":"Ashi Garg, Henry Li Xinyuan, Kevin Duh, Leibny Paola Garc\\'ia-Perera, Matthew Wiesner, Nicholas Andrews, Sanjeev Khudanpur, Zexin Cai","submitted_at":"2025-02-06T21:40:09Z","abstract_excerpt":"Most current zero-shot voice conversion methods rely on externally supervised components, particularly speaker encoders, for training. To explore alternatives that eliminate this dependency, this paper introduces GenVC, a novel framework that disentangles speaker identity and linguistic content from speech signals in a self-supervised manner. GenVC leverages speech tokenizers and an autoregressive, Transformer-based language model as its backbone for speech generation. This design supports large-scale training while enhancing both source speaker privacy protection and target speaker cloning fi"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2502.04519","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-02-06T21:40:09Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"fdd6e24ce31847c2844104f0ee0504e4a05a13b11c5e2918cc20ea157337762a","abstract_canon_sha256":"3c1cb1c011894d12c7795a9b58fd00c99bdd1e0ae70603996bef53100949e262"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:56:43.467732Z","signature_b64":"L1JMcOdXPgKIJMzI1Y2whtADo2NQO/2UVQ2s1q7S0tVR1SIzXamjEXRRKSamzOo+S0e5KhXyLlw1Ur78eHy6Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8d2432ecb9c2caaa91d999d7596c3ee849f6eeef6231a70ae04ca47ed95d5ece","last_reissued_at":"2026-07-05T11:56:43.467177Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:56:43.467177Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GenVC: Self-Supervised Zero-Shot Voice Conversion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"eess.AS","authors_text":"Ashi Garg, Henry Li Xinyuan, Kevin Duh, Leibny Paola Garc\\'ia-Perera, Matthew Wiesner, Nicholas Andrews, Sanjeev Khudanpur, Zexin Cai","submitted_at":"2025-02-06T21:40:09Z","abstract_excerpt":"Most current zero-shot voice conversion methods rely on externally supervised components, particularly speaker encoders, for training. To explore alternatives that eliminate this dependency, this paper introduces GenVC, a novel framework that disentangles speaker identity and linguistic content from speech signals in a self-supervised manner. GenVC leverages speech tokenizers and an autoregressive, Transformer-based language model as its backbone for speech generation. This design supports large-scale training while enhancing both source speaker privacy protection and target speaker cloning fi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.04519","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2502.04519/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2502.04519","created_at":"2026-07-05T11:56:43.467235+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.04519v2","created_at":"2026-07-05T11:56:43.467235+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.04519","created_at":"2026-07-05T11:56:43.467235+00:00"},{"alias_kind":"pith_short_12","alias_value":"RUSDF3FZYLFK","created_at":"2026-07-05T11:56:43.467235+00:00"},{"alias_kind":"pith_short_16","alias_value":"RUSDF3FZYLFKVEOZ","created_at":"2026-07-05T11:56:43.467235+00:00"},{"alias_kind":"pith_short_8","alias_value":"RUSDF3FZ","created_at":"2026-07-05T11:56:43.467235+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RUSDF3FZYLFKVEOZTHLVS3B65B","json":"https://pith.science/pith/RUSDF3FZYLFKVEOZTHLVS3B65B.json","graph_json":"https://pith.science/api/pith-number/RUSDF3FZYLFKVEOZTHLVS3B65B/graph.json","events_json":"https://pith.science/api/pith-number/RUSDF3FZYLFKVEOZTHLVS3B65B/events.json","paper":"https://pith.science/paper/RUSDF3FZ"},"agent_actions":{"view_html":"https://pith.science/pith/RUSDF3FZYLFKVEOZTHLVS3B65B","download_json":"https://pith.science/pith/RUSDF3FZYLFKVEOZTHLVS3B65B.json","view_paper":"https://pith.science/paper/RUSDF3FZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.04519&json=true","fetch_graph":"https://pith.science/api/pith-number/RUSDF3FZYLFKVEOZTHLVS3B65B/graph.json","fetch_events":"https://pith.science/api/pith-number/RUSDF3FZYLFKVEOZTHLVS3B65B/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RUSDF3FZYLFKVEOZTHLVS3B65B/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RUSDF3FZYLFKVEOZTHLVS3B65B/action/storage_attestation","attest_author":"https://pith.science/pith/RUSDF3FZYLFKVEOZTHLVS3B65B/action/author_attestation","sign_citation":"https://pith.science/pith/RUSDF3FZYLFKVEOZTHLVS3B65B/action/citation_signature","submit_replication":"https://pith.science/pith/RUSDF3FZYLFKVEOZTHLVS3B65B/action/replication_record"}},"created_at":"2026-07-05T11:56:43.467235+00:00","updated_at":"2026-07-05T11:56:43.467235+00:00"}